In [1]:

    

import pandas as pd
import numpy as np


    

In [2]:

    

df = pd.read_csv('data/src/sample_pandas_normal.csv')
df.iloc[1] = np.nan
print(df)


    

    




      name   age state  point
0    Alice  24.0    NY   64.0
1      NaN   NaN   NaN    NaN
2  Charlie  18.0    CA   70.0
3     Dave  68.0    TX   70.0
4    Ellen  24.0    CA   88.0
5    Frank  30.0    NY   57.0

In [3]:

    

u = df['state'].unique()
print(u)
print(type(u))


    

    




['NY' nan 'CA' 'TX']
<class 'numpy.ndarray'>

In [4]:

    

vc = df['state'].value_counts()
print(vc)
print(type(vc))


    

    




NY    2
CA    2
TX    1
Name: state, dtype: int64
<class 'pandas.core.series.Series'>

In [5]:

    

print(df['state'].value_counts(ascending=True))


    

    




TX    1
CA    2
NY    2
Name: state, dtype: int64

In [6]:

    

print(df['state'].value_counts(sort=False))


    

    




CA    2
NY    2
TX    1
Name: state, dtype: int64

In [7]:

    

print(df['state'].value_counts(dropna=False))


    

    




NY     2
CA     2
TX     1
NaN    1
Name: state, dtype: int64

In [8]:

    

print(df['state'].value_counts(dropna=False, normalize=True))


    

    




NY     0.333333
CA     0.333333
TX     0.166667
NaN    0.166667
Name: state, dtype: float64

In [9]:

    

nu = df['state'].nunique()
print(nu)
print(type(nu))


    

    




3
<class 'int'>

In [10]:

    

print(df['state'].nunique(dropna=False))


    

    




4

In [11]:

    

nu_col = df.nunique()
print(nu_col)
print(type(nu_col))


    

    




name     5
age      4
state    3
point    4
dtype: int64
<class 'pandas.core.series.Series'>

In [12]:

    

print(df.nunique(dropna=False))


    

    




name     6
age      5
state    4
point    5
dtype: int64

In [13]:

    

print(df.nunique(dropna=False, axis='columns'))


    

    




0    4
1    1
2    4
3    4
4    4
5    4
dtype: int64

In [14]:

    

print(df['state'].nunique())


    

    




3

In [15]:

    

print(df.nunique())


    

    




name     5
age      4
state    3
point    4
dtype: int64

In [16]:

    

print(df['state'].unique().tolist())
print(type(df['state'].unique().tolist()))


    

    




['NY', nan, 'CA', 'TX']
<class 'list'>

In [17]:

    

print(df['state'].value_counts().index.tolist())
print(type(df['state'].value_counts().index.tolist()))


    

    




['NY', 'CA', 'TX']
<class 'list'>

In [18]:

    

print(df['state'].value_counts(dropna=False).index.values)
print(type(df['state'].value_counts().index.values))


    

    




['NY' 'CA' 'TX' nan]
<class 'numpy.ndarray'>

In [19]:

    

print(df['state'].value_counts()['NY'])


    

    




2

In [20]:

    

print(df['state'].value_counts().NY)


    

    




2

In [21]:

    

for index, value in df['state'].value_counts().iteritems():
    print(index, ': ', value)


    

    




NY :  2
CA :  2
TX :  1

In [22]:

    

d = df['state'].value_counts().to_dict()
print(d)
print(type(d))


    

    




{'NY': 2, 'CA': 2, 'TX': 1}
<class 'dict'>

In [23]:

    

print(d['NY'])


    

    




2

In [24]:

    

for key, value in d.items():
    print(key, ': ', value)


    

    




NY :  2
CA :  2
TX :  1

In [25]:

    

print(df['state'].value_counts())


    

    




NY    2
CA    2
TX    1
Name: state, dtype: int64

In [26]:

    

print(df['state'].value_counts().index[0])


    

    




NY

In [27]:

    

print(df['state'].value_counts().iat[0])


    

    




2

In [28]:

    

print(df.apply(lambda x: x.value_counts().index[0]))


    

    




name     Frank
age         24
state       NY
point       70
dtype: object

In [29]:

    

print(df.apply(lambda x: x.value_counts().iat[0]))


    

    




name     1
age      2
state    2
point    2
dtype: int64

In [30]:

    

print(df['state'].mode())


    

    




0    CA
1    NY
dtype: object

In [31]:

    

print(df['state'].mode().tolist())


    

    




['CA', 'NY']

In [32]:

    

print(df['age'].mode().tolist())


    

    




[24.0]

In [33]:

    

s_mode = df.apply(lambda x: x.mode().tolist())
print(s_mode)


    

    




name     [Alice, Charlie, Dave, Ellen, Frank]
age                                    [24.0]
state                                [CA, NY]
point                                  [70.0]
dtype: object

In [34]:

    

print(type(s_mode))


    

    




<class 'pandas.core.series.Series'>

In [35]:

    

print(s_mode['name'])


    

    




['Alice', 'Charlie', 'Dave', 'Ellen', 'Frank']

In [36]:

    

print(type(s_mode['name']))


    

    




<class 'list'>

In [37]:

    

print(df.mode())


    

    




      name   age state  point
0    Alice  24.0    CA   70.0
1  Charlie   NaN    NY    NaN
2     Dave   NaN   NaN    NaN
3    Ellen   NaN   NaN    NaN
4    Frank   NaN   NaN    NaN

In [38]:

    

print(df.mode().count())


    

    




name     5
age      1
state    2
point    1
dtype: int64

In [39]:

    

print(df.astype('str').describe())


    

    




         name   age state point
count       6     6     6     6
unique      6     5     4     5
top     Frank  24.0    CA  70.0
freq        1     2     2     2

In [40]:

    

print(df.astype('str').describe().loc['top'])


    

    




name     Frank
age       24.0
state       CA
point     70.0
Name: top, dtype: object